In-Ho Cho

Dept: Civil, Construction and Environmental Engineering

Current Collaborators: Statistics faculty Jae-Kwang Kim and Raymond Wong for the below research topics:

  1. First topic focuses on advanced statistical learning and prediction of complex real-world responses, notably tackling a large number of variables and their interactions. The key enabling factor is the harmonious combination of advanced statistical theory and parallel computing technology.

We demonstrated promising results from recent applications to problems of FAA (Federal Aviation Administration) and Earthquake Engineering fields. Prediction accuracy and computational efficiency have proven promising. I believe this research topic will be helpful for prediction of Economics-related problems as long as there is formidable complexity in the data of a large number of variables. [Keyword: multivariate prediction, multivariable learning, data-driven learning, complex database, parallel computing for statistical prediction]

  1. Second topic focuses on curing big data by multivariate imputation theory. This research seeks to “cure” missing data of an existing database by using a rigorous statistical theory in conjunction with advanced parallel computing technology. We believe this will substantially benefit general databases of Economics-related research since the cured database will facilitate and improve fundamental data-driven research of any discipline of Economics or financial research groups. [Keyword: multivariable imputation, missing data problem, fractional hot deck imputation, parallel computing for imputation]

Email: icho at, Phone: 4-3241